{"id":"https://openalex.org/W7163986699","doi":"https://doi.org/10.1145/3748522.3779794","title":"Adaptive Multi-User Scheduling for Large Language Model Inference on HBM-Based Processing-in-Memory Accelerators","display_name":"Adaptive Multi-User Scheduling for Large Language Model Inference on HBM-Based Processing-in-Memory Accelerators","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7163986699","doi":"https://doi.org/10.1145/3748522.3779794"},"language":null,"primary_location":{"id":"doi:10.1145/3748522.3779794","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779794","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3748522.3779794","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138258219","display_name":"Chen-Lin Shi","orcid":"https://orcid.org/0009-0001-7208-9396"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chen-Lin Shi","raw_affiliation_strings":["National Taiwan University of Science and Technology, Taipei, Taiwan, Taiwan"],"raw_orcid":"https://orcid.org/0009-0001-7208-9396","affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology, Taipei, Taiwan, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064796481","display_name":"Xi-Zhu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Xi-Zhu Wang","raw_affiliation_strings":["National Taiwan University of Science and Technology, Taipei, Taiwan, Taiwan"],"raw_orcid":"https://orcid.org/0009-0005-2504-723X","affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology, Taipei, Taiwan, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013832436","display_name":"Ya-Shu Chen","orcid":"https://orcid.org/0000-0002-8698-1318"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ya-Shu Chen","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-8698-1318","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5138258219"],"corresponding_institution_ids":["https://openalex.org/I154864474"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.96940662,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1268","last_page":"1274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.4318999946117401,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.4318999946117401,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.1656000018119812,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.06469999998807907,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.52920001745224},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48179998993873596},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3488999903202057},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.2831000089645386},{"id":"https://openalex.org/keywords/simulation-language","display_name":"Simulation language","score":0.27720001339912415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190999984741211},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.52920001745224},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4171000123023987},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2847999930381775},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C141218545","wikidata":"https://www.wikidata.org/wiki/Q7521336","display_name":"Simulation language","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2596000134944916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3748522.3779794","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779794","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3748522.3779794","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779794","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W3134274954","https://openalex.org/W3189166979","https://openalex.org/W4280496502","https://openalex.org/W4388757726","https://openalex.org/W4392427708","https://openalex.org/W4401408916","https://openalex.org/W4404955001","https://openalex.org/W4408925909"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-10T14:10:52.464848","created_date":"2026-06-10T00:00:00"}
